lec03_features

lec03_features - CS6670:ComputerVision NoahSnavely...

Info icon This preview shows pages 1–25. Sign up to view the full content.

View Full Document Right Arrow Icon
Lecture 3: Feature detection and matching CS6670: Computer Vision Noah Snavely
Image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Administrivia New location: please sit in the front rows Assignment 1 (feature detection and matching) will be released right after class, due Thursday, September 24 by 11:59pm More details at the end of lecture
Image of page 2
Reading Szeliski: 4.1
Image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Why do we flip the kernel? Convolution is commutative Cross correlation is noncommutative
Image of page 4
Feature extraction: Corners and blobs
Image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Motivation: Automatic panoramas Credit: Matt Brown
Image of page 6
http://research.microsoft.com/en us/um/redmond/groups/ivm/HDView/HDGigapixel.htm HD View Also see GigaPan: http://gigapan.org/ Motivation: Automatic panoramas
Image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Why extract features? Motivation: panorama stitching We have two images – how do we combine them?
Image of page 8
Why extract features? Motivation: panorama stitching We have two images – how do we combine them? Step 1: extract features Step 2: match features
Image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Why extract features? Motivation: panorama stitching We have two images – how do we combine them? Step 1: extract features Step 2: match features Step 3: align images
Image of page 10
Image matching by Diva Sian by swashford
Image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Harder case by Diva Sian by scgbt
Image of page 12
Harder still? NASA Mars Rover images
Image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
NASA Mars Rover images with SIFT feature matches Answer below (look for tiny colored squares…)
Image of page 14
Feature Matching
Image of page 15

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Feature Matching
Image of page 16
Invariant local features Find features that are invariant to transformations geometric invariance: translation, rotation, scale photometric invariance: brightness, exposure, … Feature Descriptors
Image of page 17

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Advantages of local features Locality features are local, so robust to occlusion and clutter Quantity hundreds or thousands in a single image Distinctiveness: can differentiate a large database of objects Efficiency real time performance achievable
Image of page 18
More motivation… Feature points are used for: Image alignment (e.g., mosaics) 3D reconstruction Motion tracking Object recognition Indexing and database retrieval Robot navigation … other
Image of page 19

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon